Feature Requests

Support Chinese and Cantonese language.

I would say at least half of the edits I need to make for my transcripts are fixing issues that Descript introduces because it does bizarre things with punctuation and random capitalization of words like you, somebody, some and that after commas. Can you stop it from adding a comma every time a presenter pauses to gather their thoughts? I that's why we see extra commas, and commas in the wrong places like after an "and" or "or" or "of" instead of before one. Regardless of whether that's the cause, grammatically those commas need to come before those words, not after them. A bigger issue is it throws in commas and periods in places that would never have them. There is zero reason that there should ever be period after the words "the", "and" or "or" because humans don't end sentences with these words, but the transcripts are littered with them, and each needs to be removed. There are only a few cases that there should be a comma or period after the words "to" and never a period or comma after "a" and not only are there tons of both in transcripts, you also can't do a search and replace since you decided to only allow find whole words on words 3 letters/characters or longer! Yes, I can search for them without selecting the match the whole word filter, but when I'm looking to replace "a," it also picks up every time there's a "trauma," which is quite often considering the topic of our lectures. Also, why does it separate prefixes from the words? We don't write about re experiencing things or non compliance or co workers, but Descript renders prefixes that way and all of those need to be fixed too, as well as insisting on adding a space after the period in numbers with decimals, and both a comma and a space to all numbers in the thousands or higher, which is not how humans write either. More recently, within the past couple of months, there are a bunch of periods showing up in inappropriate places within the middle of sentences (not immediately before or after a pause, mind you, but within fluidly spoken sentences) that even Descript seems to realize are not correct, because it doesn't capitalize the next word after these periods, which ironically makes them harder to spot given the marker to indicate a pause between words looks somewhat similar to a period. I've been using this program for 3+ years, and it's frustrating how little attention transcript issues like this are still given. The AI features are great, but maybe you could get AI to fix the punctuation issues while you're at it?

When transcribing numbers like "10,000" or "120,000," Descript adds a space after the comma, yielding "10, 000" and "120, 000."

For the last six months to a year or so, I've noticed that transcripts increasingly include extraneous words or phrases that the Al has "imagined". These imagined phrases are linked either to a moment of silence in which no words are spoken, or a single syllable of audio. I think what's sometimes happening is that the Al is trying to predict the next few words in a sentence, and then inserting those words into the transcript - but it's doing that as well as transcribing the actual words spoken. Sometimes it just seems to invent and insert completely random phrases. Sometimes things like the composition title or folder name randomly appear in the middle of a sentence. Last year, I had the names of competitor transcription apps appearing in the middle of sentences! This is frustrating.

I uploaded a mandarin transcript and when I delete one sentence, the video doesn't align. Would like to be able to edit in Mandarin transcript.

Bulk caption creation and insertions into existing edited videos. obviously this would count towards the maximum transcription time for each account plan. this use case would be especially useful for editors who already have old finalized videos without captions this can be easily achieved by adding an option to export all scenes in a composition as separate files

There are various ways to achieve this goal, so I'll focus on explaining the main concept and capabilities. It's crucial to keep this separate from the 'Filler Words Tool,' and I'll elaborate on the reasons later. Before delving into the tool idea, I'd like to provide some context for my proposal. It's all one paragraph so you can skip it. I'm part of a team dedicated to safeguarding kids from potential threats posed by adults on the internet. Our approach involves setting up decoys, engaging with adults, and conducting thorough interviews as part of our investigations, that can last from 1 to 3 hours. Building rapport is our initial strategy to create a situation where the individuals believe law enforcement won't be involved, which makes confessions easy for them to talk about in depth. We record this on video as evidence for law enforcement, ensuring that any inappropriate online activities are disclosed. However, the challenge arises when law enforcement requires comprehensive information before confiscating devices or making arrests that will prevent an individual from tampering with evidence. This process of censoring 1-hour videos can extend to 4-8 hours to guarantee nothing is overlooked since youtubes guidelines are applied selectively. The proposed tool is essentially a feature to create and manage a list of words or phrases to be muted. If automating this process proves too complex, an alternative is to streamline the manual process. Users could simply right-click and select 'mute word' or 'mute words' (if multiple are highlighted). It's important to emphasize the distinction between 'word' and 'words' for clarity. To optimize loading time, this feature should be an option during media import. Activating it would expand the choice between a default list and a customized one. Users can also decide if they want the words to be highlighted and/or muted. Default lists would include words generally considered inappropriate, avoiding explicit mention to maintain context. Users adding words to the default list would automatically create a separate list comprising default words and any additions. This caters to the most common censored words on TV and addresses monetization limitations on platforms like YouTube. For user privacy, a content warning when viewing the list could be implemented. This ensures users are aware that the list may contain offensive words. Keeping this tool separate from the 'Filler Words Tool' allows for a toggle option on the timeline. When activated, users can visualize all muted sections or highlight a specific area to mute, correcting any oversights or potential misinterpretations. This information can be used to train the AI, enhancing its accuracy over time. Lastly, when users highlight and right-click any text, the menu should include an option to add it to the list. If a single word is chosen, it's treated as one entry. However, if multiple words are selected, they should also be considered as a single entry to account for context. For instance, platforms like YouTube consider context when assessing descriptive sentences—explicit details might be overlooked, but any indication involving a minor can cause a video to reach less people. Our goal isn't for entertainment purposes. It is essential for spreading awareness to parents who can find other resources to keep better eyes on their Childs online activities and even take preventative measures. Not only that, but the more these adults are caught, the easier it is to take down larger groups that actively produce the material being plagued online - leading to the rescue of REAL victims all over the world. So it's more than just a feature request in my eyes. Thanks for anyone that actually reads this. Sorry for it being so detailed. I just think many haven't gave enough thought into the actual implication of such a feature. Devs work hard and it's not as simple as many think. Ive made far more in depth mockups for InShot and PicsArt who both made the ideas into real tools. I wouldn't mind doing that as well.

I love the filler word toolkit here, but I don't see a functionality to override descript's choice of filler words. I want to be able to keep some in that descript selected as being filler words.

Descript is a great at speeding up the workflow, but since all our clients are UK based, it's really frustrating that only US English is available. Can we have UK English too please!?